© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2681
    Prev
    Next
    INDEX
    Explanations

    references to statistical performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.06
    3:0.04
    4:0.08
    5:0.03
    6:0.21
    7:0.06
    8:0.13
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
     atheist
    -4.10
     Sparkle
    -3.82
    Walker
    -3.79
     atheists
    -3.69
     sorce
    -3.66
     Chloe
    -3.59
     Assy
    -3.43
    ipal
    -3.42
     atheism
    -3.38
     ranch
    -3.33
    POSITIVE LOGITS
     Ravens
    9.19
     Baltimore
    8.83
    Baltimore
    8.80
    Raven
    7.63
     Orioles
    6.58
     Freddie
    5.46
     Maryland
    5.09
     Harbaugh
    5.06
     Raven
    4.56
    Scar
    4.48
    Activations Density 0.005%

    No Known Activations